suppressPackageStartupMessages({
library(tidyverse)
library(plotly)
library(treeio)
library(ggtree)
library(ggtreeExtra)
library(svglite)
  })

BGC table for Myxococcota

## # A tibble: 7,616 × 9
##    bgc_id           GCF   genome_id contig start   end product contig_edge class
##    <chr>            <chr> <chr>     <chr>  <dbl> <dbl> <chr>   <lgl>       <chr>
##  1 BBEO01000017.1.… 0     GCA_0013… BBEO0…     0  5749 NRPS    TRUE        NRPS 
##  2 BBEO01000114.1.… 1     GCA_0013… BBEO0…     0  3507 RiPP-l… TRUE        RiPPs
##  3 BBEO01000191.1.… 2     GCA_0013… BBEO0…     0  3019 T1PKS   TRUE        PKSI 
##  4 BBEO01000385.1.… 3     GCA_0013… BBEO0…     0  2351 NRPS    TRUE        NRPS 
##  5 BBEO01000617.1.… 4     GCA_0013… BBEO0…     0  1970 NRPS-l… TRUE        NRPS 
##  6 BBEO01000880.1.… 4782… GCA_0013… BBEO0…     0  1694 resorc… TRUE        Othe…
##  7 BBEO01000892.1.… 6;67… GCA_0013… BBEO0…     0  1685 proteu… TRUE        RiPPs
##  8 BJHF01000010.1.… 1918  GCA_0141… BJHF0… 77871 88714 RiPP-l… FALSE       RiPPs
##  9 BJHF01000022.1.… 1919  GCA_0141… BJHF0… 21748 66476 arylpo… FALSE       Othe…
## 10 BJHF01000033.1.… 1920  GCA_0141… BJHF0… 19254 59021 hglE-KS TRUE        PKSo…
## # … with 7,606 more rows

Genome table for Myxococcota

## # A tibble: 572 × 11
##    genome_id       total_bgcs bgcs_on_contig_edge gtdb_taxonomy   assembly_level
##    <chr>                <dbl>               <dbl> <chr>           <chr>         
##  1 GCA_016704525.1          8                   1 d__Bacteria;p_… Contig/Scaffo…
##  2 GCA_016704445.1         12                   3 d__Bacteria;p_… Contig/Scaffo…
##  3 GCA_016704335.1         16                   2 d__Bacteria;p_… Contig/Scaffo…
##  4 GCA_016704065.1         11                   5 d__Bacteria;p_… Contig/Scaffo…
##  5 GCA_016703535.1         13                   0 d__Bacteria;p_… Contig/Scaffo…
##  6 GCA_016703425.1         18                   0 d__Bacteria;p_… Contig/Scaffo…
##  7 GCA_016702865.1         12                   5 d__Bacteria;p_… Contig/Scaffo…
##  8 GCA_016702545.1         11                   1 d__Bacteria;p_… Contig/Scaffo…
##  9 GCA_016709225.1         20                   0 d__Bacteria;p_… Contig/Scaffo…
## 10 GCA_016708565.1         12                   2 d__Bacteria;p_… Contig/Scaffo…
## # … with 562 more rows, and 6 more variables: checkm_completeness <dbl>,
## #   checkm_contamination <dbl>, genome_size <dbl>, ncbi_bioproject <chr>,
## #   mimag_quality <chr>, source <chr>

Customize BiG-SCAPE classes and color palette

bigscape_classes <- c("Terpene",
                      "RiPPs", 
                      "NRPS",
                      "PKS-NRP_Hybrids",
                      "PKSI",
                      "PKSother", 
                      "Saccharides",
                      "Others")                             

my_classes <- c("Terpene", 
                "RiPP", 
                "NRPS", 
                "NRPS-PKS", 
                "PKS", 
                "PKS", 
                "Other", 
                "Other")

my_colors <- c("#ff8800",
               "#20c200",
               "#ff0000",
               "#dd00ff",
               "#0d00ff",
               "#757575")

QC Boxplots for the phylum Nitrospirota

What family should we focus on? Polyangiaceae is well represented by our MAGs and the references.

Overview of the phylum Myxococcota. Add number of MAGs per clade

Absence / Presence matrix for f__Polyangiaceae